Skip to main content

PostgreSQL MCP

Project description

Apache AGE MCP Server

These tools provide an interface for AI Agents to manage multiple graphs in Apache AGE. They expose tools for creating, updating, administering, and visualizing graphs.

Tool Name Description Parameters
get_or_create_graph Get or create a graph with the specified name. graph_name: str
list_graphs List all graph names in the database.
upsert_graph Upsert both vertices and edges into the specified graph (deep merge). graph_name: str, vertices: List[Dict[str, Any]], edges: List[Dict[str, Any]]
upsert_edge Insert or update an edge's properties in a graph non-destructively. graph_name: str, label: str, edge_start_ident: str, edge_end_ident: str, properties: Dict[str, Any]
upsert_vertex Insert or update a vertex's properties in a graph non-destructively. graph_name: str, vertex_ident: str, label: str, properties: Dict[str, Any]
drop_graphs Drop one or more graphs by name. graph_names: List[str]
drop_vertex Remove a vertex by ident. graph_name: str, vertex_ident: str
drop_edge Remove an edge by ident. graph_name: str, edge_ident: str
generate_visualization Generate a single-page HTML file visualizing a graph using vis.js and pyvis. graph_name: str

Server Installation

Install the latest release using pipx (recommended for CLI/server tools):

# Install
pipx install agemcp

# Postgres DSN / MCP Server Defaults
agemcp config

# Start the server
agemcp run

You should see something like this:

INFO:     Starting MCP server 'agemcp' with transport 'streamable-http' on http://0.0.0.0:8000/mcp/
INFO:     Started server process [13951]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)

Client Installation

VSCode

  1. Open Command Palette (Cmd+Shift+P or Ctrl+Shift+P).
  2. Select MCP: Add Server...
  3. Choose "HTTP" option.
  4. Enter the server URL (e.g., http://localhost:8000/mcp/).
  5. Enter a "server id" (e.g., agemcp).
  6. Select Global for the scope.
  7. Done. (It should appear in the extensions sidebar.)

Roo / Cline / Claude

{
  "mcpServers": {
    "agemcp": {
      "url": "http://localhost:8000/mcp/",
      "type": "streamable-http",
      "headers": {
        "Content-Type": "application/json"
      }
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

agemcp-0.5.0.tar.gz (60.9 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agemcp-0.5.0-py3-none-any.whl (54.2 kB view details)

Uploaded Python 3

File details

Details for the file agemcp-0.5.0.tar.gz.

File metadata

  • Download URL: agemcp-0.5.0.tar.gz
  • Upload date:
  • Size: 60.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for agemcp-0.5.0.tar.gz
Algorithm Hash digest
SHA256 e8dfef7e1b96f5ebf10d86108a84c4d5535b08d3d76ffc4a294f362d3b04a269
MD5 f1ad3c1248af3a12ab4ca405283c2a06
BLAKE2b-256 40e9b357a4a6d9fd23e2c5617d689b1b0adeeda8c883c64a86b034c3e51a2ed5

See more details on using hashes here.

File details

Details for the file agemcp-0.5.0-py3-none-any.whl.

File metadata

  • Download URL: agemcp-0.5.0-py3-none-any.whl
  • Upload date:
  • Size: 54.2 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for agemcp-0.5.0-py3-none-any.whl
Algorithm Hash digest
SHA256 1603a076c27c3fbac1e178b1ba5772c6d4d417d11c5728dd2ddf676850a18b8c
MD5 6200bf6b014a09a505f13c16de031c5c
BLAKE2b-256 c0f4d5ac6d478b286dc9b463dfeb823f0c87c8d7bd35caef1b2bb953ec22586a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page